seifbenayed1992
Joined 2 years ago
Karma
18
Submissions
24
Member since
Feb 18
Nobody exists on purpose. Nobody belongs anywhere. Everybody's gonna die. Come watch TV
View on Hacker NewsRecent submissions
Comment · 1 month ago
So I build my startup and we use to work a lot via WhatsApp which wasn't very efficient so we decide to switch via ticketing system so I use Notion, linear and add a simple artefact for my non technical team so they can grilling and create a brief which become a spec then tickets. this is mainly now for me to push small bug fixes ( for now) or simple features but maybe few things need to improve.
Comment · 7 months ago
pi-mono is a great toolkit — coding agent CLI, unified LLM API, web UI, Slack bot, vLLM pods.
cloclo is a runtime for agent toolkits. You plug it into your own agents and it gives them multi-agent orchestration (AICL protocol), 13 providers, skill registry, native browser/docs/phone tools, memory, and an NDJSON bridge. Zero native deps.
Comment · 7 months ago
Thanks! If you want to kick the tires, `npx cloclo` gets you started — works with Anthropic, OpenAI, Gemini, or local models via Ollama/LM Studio out of the box. Curious what you'd want to use it for?
Comment · 7 months ago
Local models are finally starting to feel pleasant instead of just "possible." The headless LM Studio flow is especially nice because it makes local inference usable from real tools instead of as a demo.
Related note from someone building in this space: I've been working on cloclo (https://www.npmjs.com/package/cloclo), an open-source coding agent CLI, and this is exactly the direction I'm excited about. It natively supports LM Studio, Ollama, vLLM, Jan, and llama.cpp as providers alongside cloud models, so you can swap between local and hosted backends without changing how you work.
Feels like we're getting closer to a good default setup where local models are private/cheap enough to use daily, and cloud models are still there when you need the extra capability.